Update app.py

app.py

@@ -5,6 +5,7 @@ import numpy as np
 from datasets import load_dataset, Audio
 from transformers import pipeline
 import librosa
+from openai import OpenAI
 
 # Load ASR model
 asr_pipe = pipeline(model="divakaivan/glaswegian-asr")
@@ -27,11 +28,14 @@ def transcribe(audio):
     text = asr_pipe(audio)["text"]
     return text
 
-def generate_response(text):
-    input_ids = gpt_tokenizer.encode(text, return_tensors='pt')
-    response_ids = gpt_model.generate(input_ids, max_length=100, num_return_sequences=1)
-    response_text = gpt_tokenizer.decode(response_ids[0], skip_special_tokens=True)
-    return response_text
+def generate_response(text, api_key):
+    client = OpenAI(api_key=api_key)
+    response = client.chat.completions.create(
+        model='gpt-4o-mini',
+        messages=[{"role": "user", "content": text}]
+    )
+    
+    return response.choices[0].message.content
 
 def synthesize_speech(text):
     inputs = processor(text=text, return_tensors="pt")
@@ -61,15 +65,18 @@ def create_speaker_embedding(waveform):
         speaker_embeddings = speaker_embeddings.squeeze().cpu().numpy()
     return speaker_embeddings
 
-def voice_assistant(audio):
+def voice_assistant(audio, api_key):
     transcribed_text = transcribe(audio)
-    response_text = generate_response(transcribed_text)
+    response_text = generate_response(transcribed_text, api_key)
     speech_audio = synthesize_speech(response_text)
     return speech_audio
 
 iface = gr.Interface(
     fn=voice_assistant,
-    inputs=gr.Audio(type="filepath"),
+    inputs=[
+        gr.Audio(type="filepath"),
+        gr.Textbox(label="OpenAI API Key", type="password") 
+    ],
     outputs=gr.Audio(label="Response Speech", type="numpy"),
     title="Your Glaswegian Assistant"
 )